1）贝叶斯正则化方法 所谓贝叶斯正则化（Bayesian-Regularization，BR）是指通过修正神经网络的 性能函数来提高其推广能力的过程【54555657】。
基于2个网页-相关网页
Bayesian regularization method 贝叶斯规则化方法
bayesian-regularization algorithm 贝叶斯正则化算法
Bayesian regularization algorithm Bayesian正则化
bayesian regularization algorithms 贝叶斯正则化
bayesian-regularization neural network 贝叶斯正则化神经网络
bayesian-regularization neural networks 贝叶斯正则化神经网络
Bayesian-regularization BP neural network Bayesian正则化BP神经网络
And using this model can simply the structure of neural networks and reduce training time. At the same time, owing to using Bayesian regularization methods to optimize neural networks, the generalization ability of neural networks is improved.
为了提高神经网络的泛化能力,本文采用贝叶斯正则化的方法来优化神经网络。
参考来源 - 供应链环境下供应商选择之研究To counter the over-fitting problem in BP algorithm and its improvements, we proposed method which was raising the generalization of the network of BP. Based on Bayesian-regularization BP algorithm is put forward.
针对BP算法及其改进算法中出现的过拟合(over-fitting)问题,探讨了提高BP神经网络泛化能力的方法,提出了基于贝叶斯正规化(Bayesian regularization),的算法,在网络目标函数中引入表示网络结构复杂性的惩罚项,使得在训练优化的过程中降低网络结构的复杂性,并通过贝叶斯推理得出目标函数的最优化参数,达到避免网络过拟合的目的。
参考来源 - 基于贝叶斯正则化BP神经网络的上市公司财务困境预警模型Using Bayesian regularization neural networks to do error data correction experiments measured by the trajectory meter,the results are analyzed and summed up.
采用贝叶斯正则化神经网络对该运动轨迹测量仪的实测数据进行误差修正实验,并对实验结果进行分析和总结。
参考来源 - Bayesian算法在某运动轨迹测量仪中的应用研究·2,447,543篇论文数据，部分数据来源于NoteExpress
The cohesive energy, of 61 metallic crystalloid is predicted by using Bayesian-Regularization neural networks(BRNN).
采用贝叶斯正则化神经网络（BRNN）对61种金属晶体结合能进行了预测。
The BPNN model of Bayesian regularization method was adopted to create the adaptivity and generalization of BPNN.
文中采用贝叶斯正则化与BP网络结合的方法，建立动态前馈校正模型。
In the Bayesian neural network, Bayesian regularization technique has been used to study the structure of neural network.
在贝叶斯神经网络中，贝叶斯正则化技术被用来学习神经网络结构。
应用推荐